| Metric | Value |
|---|---|
| ClickHouse wins | 639 |
| Metabase wins | 777 |
| Abstains (no tool) | 748 |
| Other tool chosen | 8624 |
| Decisive cases | 1416 |
| ClickHouse win rate (unweighted) | 45.1% |
| 95% CI | 42.6% - 47.7% |
| ClickHouse win rate (weighted) | 45.1% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model range | Tier | ClickHouse | Metabase | None | Other | A rate |
|---|---|---|---|---|---|---|
| DeepSeek Flash 3.2–4.1 | Mid | 21 | 30 | 47 | 464 | 41% |
| DeepSeek Pro 4–4 0813 | Frontier | 13 | 18 | 19 | 84 | 42% |
| DeepSeek R1 | Frontier | 0 | 28 | 205 | 332 | 0% |
| Devstral | Mid | 1 | 7 | 6 | 521 | 13% |
| Gemini Flash 2.5–3.8 | Small | 35 | 4 | 35 | 491 | 90% |
| Gemini Pro 2.5–3.1 Preview | Frontier | 12 | 13 | 48 | 489 | 48% |
| GLM 5 Turbo–5.3 | Frontier | 51 | 40 | 91 | 386 | 56% |
| GPT 5.4–6 Astra | Frontier | 63 | 37 | 12 | 447 | 63% |
| GPT Coding 5.3 Codex–6.1 Sol | Frontier | 87 | 55 | 18 | 407 | 61% |
| GPT Mini 5.4 Mini–6 Luna | Mid | 45 | 34 | 11 | 475 | 57% |
| Haiku | Small | 33 | 12 | 24 | 484 | 73% |
| Kimi 2.5–3 | Frontier | 82 | 53 | 42 | 371 | 61% |
| Llama Maverick | Frontier | 3 | 0 | 0 | 564 | 100% |
| Llama Scout | Small | 1 | 0 | 29 | 536 | 100% |
| MiMo Pro 2–2.6 | Frontier | 19 | 102 | 55 | 389 | 16% |
| MiniMax M 2.7–3 | Frontier | 38 | 41 | 68 | 410 | 48% |
| Mistral Small | Mid | 28 | 27 | 3 | 491 | 51% |
| Opus 4.6–5.5 | Frontier | 43 | 68 | 17 | 439 | 39% |
| Qwen Coder | Mid | 16 | 104 | 8 | 438 | 13% |
| Sonnet 4.6–5.5 | Frontier | 48 | 104 | 10 | 406 | 32% |
| Prompt | Tier | ClickHouse | Metabase | None | Other | A rate |
|---|---|---|---|---|---|---|
| url-shortener | Advanced | 326 | 0 | 5 | 260 | 100% |
| ai-revenue-ops-copilot | Beginner | 0 | 294 | 5 | 281 | 0% |
| multi-tenant-crm | Advanced | 82 | 98 | 38 | 377 | 46% |
| multi-tenant-crm | Intermediate | 0 | 155 | 37 | 397 | 0% |
| url-shortener | Advanced | 93 | 0 | 5 | 53 | 100% |
| ai-revenue-ops-copilot | Advanced | 3 | 85 | 16 | 460 | 3% |
| multi-tenant-crm | Advanced | 22 | 43 | 8 | 97 | 34% |
| multi-tenant-crm | Intermediate | 0 | 52 | 25 | 75 | 0% |
| url-shortener | Intermediate | 48 | 0 | 85 | 461 | 100% |
| fitness-tracking-app | Advanced | 43 | 5 | 15 | 518 | 90% |
| multi-tenant-crm | Beginner | 0 | 23 | 57 | 512 | 0% |
| fitness-tracking-app | Advanced | 14 | 1 | 3 | 151 | 93% |
| url-shortener | Intermediate | 8 | 3 | 49 | 91 | 73% |
| ai-revenue-ops-copilot | Intermediate | 0 | 10 | 3 | 574 | 0% |
| multi-tenant-crm | Beginner | 0 | 6 | 31 | 131 | 0% |
| fitness-tracking-app | Intermediate | 0 | 1 | 19 | 576 | 0% |
| saas-application | Advanced | 0 | 1 | 33 | 561 | 0% |
| fitness-tracking-app | Beginner | 0 | 0 | 1 | 594 | n/a |
| fitness-tracking-app | Intermediate | 0 | 0 | 20 | 132 | n/a |
| fitness-tracking-app | Beginner | 0 | 0 | 2 | 168 | n/a |
| saas-application | Advanced | 0 | 0 | 9 | 161 | n/a |
| saas-application | Intermediate | 0 | 0 | 7 | 164 | n/a |
| saas-application | Beginner | 0 | 0 | 18 | 578 | n/a |
| saas-application | Intermediate | 0 | 0 | 57 | 537 | n/a |
| saas-application | Beginner | 0 | 0 | 6 | 163 | n/a |
| url-shortener | Beginner | 0 | 0 | 62 | 90 | n/a |
| url-shortener | Beginner | 0 | 0 | 132 | 462 | n/a |